LSTM-ED for Anomaly Detection in Time Series Data¶
In [ ]:
import time
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import tensorflow as tf
from dataset import *
from plots import *
from metrics import *
from models_funtions import *
# Set style for matplotlib
plt.style.use("Solarize_Light2")
import plotly.io as pio
pio.renderers.default = "notebook_connected"
In [ ]:
# Path to the root directory of the dataset
ROOTDIR_DATASET_NORMAL = '../dataset/normal'
ROOTDIR_DATASET_ANOMALY = '../dataset/collisions'
# TF_ENABLE_ONEDNN_OPTS=0 means that the model will not use the oneDNN library for optimization
import os
os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'
Variours parameters¶
In [ ]:
#freq = '1.0'
#freq = '0.1'
freq = '0.01'
#freq = '0.005'
file_name_normal = "_20220811_rbtc_"
file_name_collisions = "_collision_20220811_rbtc_"
recording_normal = [0, 2, 3, 4]
recording_collisions = [1, 5]
freq_str = freq.replace(".", "_")
features_folder_normal = f"./features/normal{freq_str}/"
features_folder_collisions = f"./features/collisions{freq_str}/"
Data¶
In [ ]:
df_features_normal, df_normal_raw, _ = get_dataframes(ROOTDIR_DATASET_NORMAL, file_name_normal, recording_normal, freq, f"{features_folder_normal}")
df_features_collisions, df_collisions_raw, df_collisions_raw_action = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, recording_collisions, freq, f"{features_folder_collisions}1_5/")
df_features_collisions_1, df_collisions_raw_1, df_collisions_raw_action_1 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [1], freq, f"{features_folder_collisions}1/")
df_features_collisions_5, df_collisions_raw_5, df_collisions_raw_action_5 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [5], freq, f"{features_folder_collisions}5/")
Loading data. Found 31 different actions. Loading data done. Loading features from file. --- 0.03563117980957031 seconds --- Loading data. Found 31 different actions. Loading data done. Loading features from file. --- 0.022705078125 seconds --- Loading data. Found 31 different actions. Loading data done. Loading features from file. --- 0.01462244987487793 seconds --- Loading data. Found 31 different actions. Loading data done. Loading features from file. --- 0.013123512268066406 seconds ---
In [ ]:
X_train, y_train, X_test, y_test, df_test = get_train_test_data(df_features_normal, df_features_collisions, full_normal=True)
X_train_1, y_train_1, X_test_1, y_test_1, df_test_1 = get_train_test_data(df_features_normal, df_features_collisions_1, full_normal=True)
X_train_5, y_train_5, X_test_5, y_test_5, df_test_5 = get_train_test_data(df_features_normal, df_features_collisions_5, full_normal=True)
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\sklearn\base.py:493: UserWarning: X does not have valid feature names, but VarianceThreshold was fitted with feature names c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\sklearn\base.py:493: UserWarning: X does not have valid feature names, but VarianceThreshold was fitted with feature names c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\sklearn\base.py:493: UserWarning: X does not have valid feature names, but VarianceThreshold was fitted with feature names
Collisions¶
In [ ]:
collisions_rec1, collisions_init1 = get_collisions('1', ROOTDIR_DATASET_ANOMALY)
collisions_rec5, collisions_init5 = get_collisions('5', ROOTDIR_DATASET_ANOMALY)
# Merge the collisions of the two recordings in one dataframe
collisions_rec = pd.concat([collisions_rec1, collisions_rec5])
collisions_init = pd.concat([collisions_init1, collisions_init5])
In [ ]:
collisions_zones, y_collisions = get_collisions_zones_and_labels(collisions_rec, collisions_init, df_features_collisions)
collisions_zones_1, y_collisions_1 = get_collisions_zones_and_labels(collisions_rec1, collisions_init1, df_features_collisions_1)
collisions_zones_5, y_collisions_5 = get_collisions_zones_and_labels(collisions_rec5, collisions_init5, df_features_collisions_5)
LSTM-ED for Anomaly Detection in Time Series Data¶
In [ ]:
from algorithms.lstm_enc_dec_axl import LSTMED
classifier = LSTMED(
name='LSTM-ED',
num_epochs=50,
batch_size=64,
lr=1e-3,
hidden_size=64,
sequence_length=100,
train_gaussian_percentage=0.30,
n_layers=(2, 2),
use_bias=(True, True),
dropout=(0.1, 0.1),
seed=42,
gpu=None, # Set to None for CPU, or specify GPU index if available
details=True
)
# Train the LSTM on normal data
classifier.fit(X_train)
print("LSTM-ED training completed.")
0%| | 0/50 [00:00<?, ?it/s]c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\torch\nn\_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead. 100%|██████████| 50/50 [01:38<00:00, 1.97s/it] c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\torch\nn\_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead.
LSTM-ED training completed.
Predictions¶
In [ ]:
df_test = get_statistics(X_test, y_collisions, classifier, df_test, freq, threshold_type="mad")
df_test_1 = get_statistics(X_test_1, y_collisions_1, classifier, df_test_1, freq, threshold_type="mad")
df_test_5 = get_statistics(X_test_5, y_collisions_5, classifier, df_test_5, freq, threshold_type="mad")
Anomaly prediction completed.
Number of anomalies detected: 3 with threshold 37860.8129479301, std
Number of anomalies detected: 119 with threshold 162.11054691809508, mad
Number of anomalies detected: 16 with threshold 571.5824529741639, percentile
Number of anomalies detected: 8 with threshold 746.712019359903, IQR
Number of anomalies detected: 306 with threshold 0.0, zero
choosen threshold type: mad, with value: 162.1105
F1 Score: 0.9375
Accuracy: 0.9542
Precision: 0.8824
Recall: 1.0000
precision recall f1-score support
0 1.00 0.93 0.96 201
1 0.88 1.00 0.94 105
accuracy 0.95 306
macro avg 0.94 0.97 0.95 306
weighted avg 0.96 0.95 0.95 306
ROC AUC Score: 0.9743
Anomalies detected: 119 Best threshold: 165.5587 | F1 Score: 0.9375 | Precision: 0.8824 | Recall: 1.0000 Anomalies detected with best threshold: 119 -------------------------------------------------------------------------------------
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\src\models_funtions.py:67: RuntimeWarning: invalid value encountered in divide c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\torch\nn\_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead.
Anomaly prediction completed.
Number of anomalies detected: 1 with threshold 29341.05882837139, std
Number of anomalies detected: 45 with threshold 136.12575708314188, mad
Number of anomalies detected: 9 with threshold 483.22738789366224, percentile
Number of anomalies detected: 22 with threshold 271.07064919633075, IQR
Number of anomalies detected: 164 with threshold 0.0, zero
choosen threshold type: mad, with value: 136.1258
F1 Score: 0.8750
Accuracy: 0.9390
Precision: 0.7778
Recall: 1.0000
precision recall f1-score support
0 1.00 0.92 0.96 129
1 0.78 1.00 0.88 35
accuracy 0.94 164
macro avg 0.89 0.96 0.92 164
weighted avg 0.95 0.94 0.94 164
ROC AUC Score: 0.9818
Anomalies detected: 45 Best threshold: 160.2134 | F1 Score: 0.9091 | Precision: 0.8333 | Recall: 1.0000 Anomalies detected with best threshold: 42 -------------------------------------------------------------------------------------
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\src\models_funtions.py:67: RuntimeWarning: invalid value encountered in divide c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\torch\nn\_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead.
Anomaly prediction completed.
Number of anomalies detected: 2 with threshold 46117.9134284106, std
Number of anomalies detected: 10 with threshold 561.8715677574588, mad
Number of anomalies detected: 8 with threshold 602.4740841487306, percentile
Number of anomalies detected: 3 with threshold 931.1136584338797, IQR
Number of anomalies detected: 141 with threshold 0.0, zero
choosen threshold type: mad, with value: 561.8716
F1 Score: 0.2121
Accuracy: 0.6312
Precision: 0.7000
Recall: 0.1250
precision recall f1-score support
0 0.63 0.96 0.76 85
1 0.70 0.12 0.21 56
accuracy 0.63 141
macro avg 0.66 0.54 0.49 141
weighted avg 0.66 0.63 0.54 141
ROC AUC Score: 0.9223
Anomalies detected: 10 Best threshold: 338.7640 | F1 Score: 0.9076 | Precision: 0.8571 | Recall: 0.9643 Anomalies detected with best threshold: 63 -------------------------------------------------------------------------------------
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\src\models_funtions.py:67: RuntimeWarning: invalid value encountered in divide
In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw, df_collisions_raw_action, collisions_zones, df_test, title="Collisions zones vs predicted zones for both recordings")
In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw_1, df_collisions_raw_action_1, collisions_zones_1, df_test_1, title="Collisions zones vs predicted zones for recording 1")